WO2023097761A1 - 一种基于语音控制的终端设备及语音控制系统 - Google Patents

一种基于语音控制的终端设备及语音控制系统 Download PDF

Info

Publication number
WO2023097761A1
WO2023097761A1 PCT/CN2021/137611 CN2021137611W WO2023097761A1 WO 2023097761 A1 WO2023097761 A1 WO 2023097761A1 CN 2021137611 W CN2021137611 W CN 2021137611W WO 2023097761 A1 WO2023097761 A1 WO 2023097761A1
Authority
WO
WIPO (PCT)
Prior art keywords
unit
voice
control
terminal device
signal
Prior art date
Application number
PCT/CN2021/137611
Other languages
English (en)
French (fr)
Inventor
高向阳
程俊
任子良
张锲石
康宇航
郭海光
Original Assignee
中国科学院深圳先进技术研究院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2023097761A1 publication Critical patent/WO2023097761A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/22—Interactive procedures; Man-machine interfaces

Definitions

  • the present application belongs to the technical field of speech recognition, and in particular relates to a terminal device and a speech control system based on speech control.
  • voice control of the terminal device can be realized by building a speech recognition algorithm in the control unit of the terminal device (eg, robot), thereby realizing intelligent control of the terminal device and improving the control efficiency of the terminal device.
  • the control unit of the terminal device eg, robot
  • the existing terminal device In order to improve the accuracy of speech recognition of the terminal device, the existing terminal device usually requires the user to input a specific wake-up word to wake up its speech recognition function, and the terminal device starts the speech recognition operation after the speech recognition function of the terminal device is awakened.
  • the control unit in the existing terminal equipment needs to monitor whether the user inputs the wake-up call all the time, which will occupy more processing resources of the control unit, reduce the resource utilization rate of the control unit, and increase the power consumption of the control unit.
  • the embodiment of the present application provides a terminal device based on voice control and a voice control system to solve the problem that the control unit in the existing terminal device needs to monitor whether there is a wake-up word input at all times, which occupies more processing resources of the control unit. This leads to the technical problems of low resource utilization and high power consumption of the control unit.
  • the embodiment of the present application provides a terminal device based on voice control, including:
  • a voice collection unit used for collecting voice signals
  • a wake-up word recognition unit connected to the voice collection unit the wake-up word recognition unit is used to identify the voice signal, and sends an interrupt to the control unit when it is recognized that the voice signal includes a preset wake-up word Signal;
  • the control unit is connected to the wake-up word recognition unit, and the control unit is used to start listening to the voice instruction from the wake-up word recognition unit when receiving the interrupt signal, and when receiving the voice instruction A control instruction corresponding to the voice instruction is generated.
  • the terminal device further includes a voice signal processing unit connected between the voice collection unit and the wake-up word recognition unit; the voice signal processing unit is configured to preprocess the voice signal, and Sending the preprocessed voice signal to the wake-up word recognition unit; the preprocessing includes filtering processing and signal amplification processing.
  • the terminal device further includes a communication unit connected to the control unit; the terminal device is connected to at least one controlled device through the communication unit;
  • the control unit is configured to send the control instruction to the communication unit when the control instruction is a control instruction for the controlled device;
  • the communication unit is configured to receive the control instruction from the control unit, and send the control instruction to the controlled device.
  • the terminal device further includes a motor drive unit, a motor, and a motion component;
  • the motor drive unit is connected to the control unit, and the motor is connected to the motor drive unit and the motion component;
  • the control unit is configured to send the control command to the motor drive unit when the control command is a motion command for the terminal device where the control unit is located;
  • the motor drive unit is used to drive the motor to run based on the control command, so as to drive the moving component to move accordingly.
  • the terminal device further includes an audio output unit connected to the control unit; the control unit is configured to generate an audio signal carrying a reply when receiving the interrupt signal, and output the audio signal to the audio the unit sends the audio signal;
  • the audio output unit is used to receive the audio signal and play the reply.
  • a status indication unit connected to the control unit is also included;
  • the status indication unit is used to indicate the status of the terminal device where the control unit is located through an indicator light.
  • the voice collection unit is a microphone array composed of a plurality of microphones.
  • the plurality of microphones are arranged linearly, and there is a preset distance between two adjacent microphones.
  • the wake-up word recognition unit includes an analog-to-digital conversion unit and a digital signal processing unit;
  • the analog-to-digital conversion unit is used to convert the voice signal into a voice command in the form of a digital signal;
  • the voice command carries beam information corresponding to the microphone array;
  • the beam information is used to describe each of the microphones The time when the voice signal is received and the position of each of the microphones;
  • the digital signal processing unit is configured to determine the position range of the sound source corresponding to the voice signal based on the beam information, and perform voice enhancement processing on the voice command based on the position range, and send the voice command to the control unit Send the voice instruction after voice enhancement processing.
  • the embodiment of the present application provides a voice control system, including at least one controlled device and the terminal device based on voice control as described in the first aspect or any optional mode of the first aspect, the terminal A device is connected to the at least one controlled device.
  • a wake-up word recognition unit for recognizing voice signals is provided between the voice collection unit and the control unit, and the wake-up word recognition unit recognizes that the voice signal includes
  • an interrupt signal is sent to the control unit; the control unit starts to monitor the voice command from the wake-up word recognition unit after receiving the interrupt signal, that is, the wake-up word monitoring operation in this application is identified by the wake-up word
  • the unit is completed, and the control unit starts the speech recognition function after the wake-up word recognition unit listens to the preset wake-up word, so that it will not occupy more processing resources of the control unit, improve the resource utilization rate of the control unit, and reduce the cost of the control unit. power consumption.
  • FIG. 1 is a schematic structural diagram of a terminal device based on voice control provided by an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of a terminal device based on voice control provided by another embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of a voice control system provided by an embodiment of the present application.
  • first and second are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features.
  • definition of “first” and “second” features may expressly or implicitly include one or more of these features.
  • references to "one embodiment” or “some embodiments” or the like in this specification means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application.
  • appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in other embodiments,” etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean “one or more but not all embodiments” unless specifically stated otherwise.
  • the terms “including”, “comprising”, “having” and variations thereof mean “including but not limited to”, unless specifically stated otherwise.
  • the embodiment of the present application firstly provides a terminal device based on voice control.
  • the terminal device may be a robot or an audio device or the like.
  • FIG. 1 is a schematic structural diagram of a terminal device based on voice control provided by an embodiment of the present application.
  • the terminal device 100 may include a voice collection unit 11 , a wake-up word recognition unit 12 and a control unit 13 .
  • the wake-up word recognition unit 12 is connected with the voice collection unit 11 and the control unit 13 .
  • the speech collection unit 11 is used to collect speech signals.
  • the voice collection unit 11 may include at least one microphone.
  • the voice collection unit 11 can collect voice signals through the at least one microphone, and send the collected voice signals to the wake-up word recognition unit 12 .
  • the number and arrangement of the microphones can be set according to actual needs.
  • the wake-up word recognition unit 12 is configured to recognize the voice signal, and send an interrupt signal to the control unit 13 when it recognizes that the voice signal includes a preset wake-up word.
  • the wake-up word recognition unit 12 may recognize the voice signal from the voice collection unit 11 based on a voice recognition algorithm, and determine whether the voice signal includes a preset wake-up word.
  • the preset wake-up words are used to wake up the voice control function of the terminal device 100 .
  • the preset wake-up language can be a word, a word or a sentence, etc., which can be set according to actual needs, and there is no special limitation here.
  • the preset wake-up language may be "Xiao Q Xiao Q".
  • the wake-up word recognition unit 12 when the wake-up word recognition unit 12 determines that the voice signal includes a preset wake-up word, it may send an interrupt signal to the control unit 13 . In another embodiment of the present application, when the wake-up word recognition unit 12 determines that the voice signal does not include the preset wake-up word, it may not respond to the voice signal and continue to receive voice signals from the voice collection unit 11 until When it is recognized that the voice signal includes a preset wake-up word, an interrupt signal is sent to the control unit 13 .
  • the wake-up word recognition unit 12 may send an interrupt signal to the control unit 13 through a hardware interrupt, or may send an interrupt signal to the control unit 13 through a software interrupt. Specifically, it can be set according to actual requirements, and there is no special limitation here.
  • the wake-up word recognition unit 12 After the wake-up word recognition unit 12 sends an interrupt signal to the control unit 13, if the voice signal from the voice collection unit 11 is received again, the voice signal can be converted into a corresponding voice command, and the voice command can be sent to the control unit 13 .
  • the voice signal is an analog signal
  • the voice command is a digital signal corresponding to the voice signal.
  • the wake-up word recognition unit 12 can perform analog-to-digital conversion processing on the voice signal, and then obtain the voice command corresponding to the voice signal.
  • control unit 13 is configured to start monitoring the voice instruction from the wake-up word recognition unit 12 when receiving the interrupt signal, and generate a control instruction corresponding to the voice instruction when receiving the voice instruction.
  • control instruction may include a control instruction for the terminal device itself, for example, a movement instruction.
  • the motion instruction may include motion parameters of the terminal device, for example, the motion route, motion speed, and/or rotational angular velocity of the terminal device.
  • the terminal device 100 can control itself by executing the control instruction.
  • control instruction may include a control instruction for other devices connected to the terminal device.
  • control unit 13 may send control instructions to other devices, so as to control other devices.
  • control unit 13 can include a micro-processing unit (micro controller unit, MCU), a single-chip microcomputer or an advanced RISC Machines (Advanced RISC Machines, ARM), etc., which can be set according to actual needs, and will not be discussed here. Do special limitation.
  • MCU micro-processing unit
  • MCU single-chip microcomputer
  • advanced RISC Machines Advanced RISC Machines, ARM
  • a wake-up word recognition unit for recognizing voice signals is provided between the voice collection unit and the control unit, and the voice signal is recognized by the wake-up word recognition unit
  • an interrupt signal is sent to the control unit; the control unit starts to monitor the voice instructions from the wake-up word recognition unit after receiving the interrupt signal, that is, the wake-up word monitoring operation in this application is performed by the wake-up
  • the speech recognition unit is completed, and the control unit starts the speech recognition function after the wake-up speech recognition unit listens to the preset wake-up speech, thereby not occupying more processing resources of the control unit, improving the resource utilization rate of the control unit, and reducing the Control unit power consumption.
  • FIG. 2 is a schematic structural diagram of a terminal device based on voice control provided by another embodiment of the present application.
  • the speech collection unit 11 in this embodiment may be a microphone array composed of multiple microphones (microphone 1 -microphone n).
  • the plurality of microphones may be arranged linearly, with a certain distance between every two adjacent microphones.
  • the plurality of microphones may also be arranged in other manners.
  • the position range of the sound source can be calculated by using the time information when the voice signal reaches each microphone and the position information of each microphone.
  • the microphone transmits the voice signal to the wake-up word recognition unit 12, it also transmits the time when it collects the voice signal.
  • the wake-up word recognition unit 12 can calculate the position range of the sound source according to the time when each microphone collects the voice signal and the position information of each microphone, and then perform voice enhancement processing on the voice signal within the position range, and perform voice enhancement processing on the voice signal outside the position range.
  • the speech signal is filtered out.
  • the location information of each microphone can be stored in the wake-up word recognition unit 12 .
  • a microphone array is used to collect voice signals, the sound source is positioned using the strong directivity of the microphone array, and the voice signal within the range of the sound source is enhanced, and the voice signal outside the range of the sound source is located.
  • the signal is filtered out, which can reduce the interference of environmental noise on the voice signal, improve the accuracy of voice recognition of terminal equipment, and make voice control more precise.
  • the terminal device 100 based on voice control further includes a voice signal processing unit 14 connected between the voice collection unit 11 and the wake-up word recognition unit 12 .
  • the voice signal processing unit 14 is used for preprocessing the voice signal, and sending the preprocessed voice signal to the wake-up word recognition unit 12 .
  • preprocessing may include filtering processing and signal amplification processing.
  • the speech signal processing unit 14 may include a filter circuit 141 and a signal amplification circuit 142 .
  • the filter circuit 141 may be a hardware filter circuit (for example, a filter circuit composed of components such as resistors and capacitors), or a finished product filter, which is not specifically limited here.
  • the signal amplifying circuit 142 may be a hardware signal amplifying circuit.
  • the signal amplifying circuit 142 may include a low noise amplifier.
  • the noise (such as environmental noise) in the voice signal can be filtered out and the voice signal can be amplified, thereby improving the wake-up word recognition unit and the wake-up word recognition unit. Speech recognition accuracy of the control unit.
  • the terminal device 100 based on voice control further includes a communication unit 15 connected to the control unit 13.
  • the terminal device can be connected with at least one controlled device via the communication unit 15 .
  • the controlled device may be a smart home device, including but not limited to: smart lights, air conditioners, refrigerators, washing machines, clothes racks, curtains, TVs, and video monitors.
  • the number of controlled devices can be set according to actual needs, and there is no special limitation here.
  • the communication unit 15 may be a wireless communication unit, for example, it may be a communication unit based on a wireless fidelity (wireless fidelity, WIFI) protocol, a communication unit based on a ZigBee (ZigBee) protocol or a Bluetooth protocol. unit.
  • a wireless fidelity wireless fidelity, WIFI
  • ZigBee ZigBee
  • the communication unit 15 may be a wired communication unit, for example, may be a Universal Serial Bus (Universal Serial Bus, USB) interface unit.
  • USB Universal Serial Bus
  • control unit 13 is configured to send the control command to the communication unit 15 when the control command is a control command for the controlled device.
  • the communication unit 15 is used for receiving control instructions from the control unit 13 and sending control instructions to the controlled device.
  • control unit 13 since the control unit 13 needs to send the control command to the controlled device connected to the terminal device, the control unit 13 needs a communication protocol between the terminal device and the controlled device when generating the control command, that is, the control unit 13
  • the data structure of the generated control command should meet the requirements of the communication protocol.
  • control instruction may be shown in Table 1 below.
  • the data header is the start byte of the control command, which is used to indicate the beginning of the control command.
  • the data header can be represented by two bytes (ie Byte0 and Byte1).
  • Byte0 and Byte1 may be the hexadecimal number 0xF8 (ie, the binary number 11111000).
  • the data length is used to indicate the effective data length of the control command, that is, the length of all bytes including the data header in Table 1.
  • the function code is used to indicate the function category realized by the control instruction. Functions of different categories are uniquely identified by this function code. Exemplarily, the definition of the function code can be as follows:
  • the function code is the hexadecimal number 0x00, it means that it is used to realize the motion control function of the terminal equipment.
  • the function code is a hexadecimal number 0x01, it means that it is used to realize the control function of the smart light.
  • the function code is the hexadecimal number 0x02, it means that it is used to realize the control function of the air conditioner.
  • the function code is a hexadecimal number 0x03, it means that it is used to realize the control function of the refrigerator.
  • the function code is a hexadecimal number 0x04, it means that it is used to realize the control function of the washing machine.
  • the function code is the hexadecimal number 0x05, it means that it is used to realize the control function of the drying rack.
  • the function code is the hexadecimal number 0x06, it means that it is used to realize the control function of the curtain.
  • the function code is the hexadecimal number 0x07, it means that it is used to realize the control function of the TV.
  • the function code is the hexadecimal number 0x08, it means that it is used to realize the control function of the video monitor.
  • Data bits are used to record effective control content.
  • the effective control content is used to describe the control method for the target device, that is, how to control the target device.
  • the length of the data bit varies according to the control content, and can be determined according to actual needs, and there is no special limitation on the length of the data bit here.
  • the target device may be the terminal device 100 itself, or a controlled device connected to the terminal device 100 .
  • the check code is used to verify the validity of the control command.
  • the verification code may be generated based on a preset verification code generation strategy.
  • the verification code generation strategy may be as follows: starting from the first byte of the control instruction, performing an XOR operation on the first byte in the control instruction and the second byte to obtain the first XOR value ;Exclusive OR operation is performed on the first XOR value and the third byte to obtain the second XOR value; and so on until the n-1th XOR value is obtained, and the n-1th XOR value is obtained or a value as a checksum.
  • the controlled device After the controlled device receives the data, it can first identify the control command through the data header, and then identify whether the control command is aimed at the current controlled device itself based on the function code in the control command. If the control command is aimed at the current controlled device itself, the validity of the control command is verified based on the check code in the control command, and the corresponding control is realized based on the data bits in the control command after it is determined that the control data is valid.
  • the terminal device by adding a communication unit to the terminal device, the terminal device can be connected to the controlled device through the communication unit, thereby realizing voice control of the controlled device.
  • the terminal device 100 based on voice control further includes a motor drive unit 16 , a motor 17 and a motion component 18 .
  • the motor driving unit 16 is connected with the control unit 13
  • the motor 17 is connected with the motor driving unit 16 and the moving assembly 18 .
  • control unit 13 is configured to send the control command to the motor drive unit 16 when the control command is a motion command for the terminal device itself.
  • the control instruction may carry motion parameters of the terminal device, for example, the motion route, motion speed, and/or rotational angular velocity of the terminal device.
  • the motor drive unit 16 is used to drive the motor 17 to run based on the control command, so as to drive the motion assembly 18 to move accordingly.
  • the terminal device 100 based on voice control further includes an audio output unit 19 connected to the control unit 13.
  • the control unit 13 is configured to generate an audio signal carrying a reply when receiving the interrupt signal, and send the audio signal to the audio output unit 19 .
  • the audio output unit 19 is used for receiving the audio signal and playing the reply words in the audio signal.
  • the purpose of the audio output unit 19 playing the reply is to inform the user that the voice monitoring function of the terminal device has been enabled, and the user can start voice control of the terminal device.
  • the reply language can be set according to actual needs, and there is no special limitation here.
  • the reply language can be "consonance and harmony".
  • the audio output unit 19 may include a signal amplifying circuit and a speaker (not shown).
  • the signal amplifying circuit is connected with the control unit 13 and the loudspeaker.
  • the signal amplifying circuit is used for amplifying the audio signal carrying the reply, and sending the amplified audio signal to the loudspeaker.
  • the loudspeaker is used to play the reply words in the audio signal.
  • an audio output unit is provided in the terminal device, and the audio output unit outputs a reply corresponding to the voice signal sent by the user, so that the user can know the status of the terminal device in time.
  • the terminal device 100 based on voice control further includes a status indication unit 20 connected to the control unit 13 .
  • the state indicating unit 20 is used for indicating the state of the terminal device 100 through an indicator light.
  • the state of the terminal device 100 includes but not limited to the voice monitoring state of the control unit 13 in the terminal device 100 .
  • the state indication unit 20 may include a light-emitting diode (light-emitting diode, LED), and indicate different states of the terminal device by controlling the LED to emit light of different colors.
  • a light-emitting diode light-emitting diode, LED
  • the wake-up word recognition unit 12 may include an analog-to-digital conversion unit 121 and a digital signal processing unit 122 .
  • the analog-to-digital conversion unit 121 is configured to convert the voice signal into a voice command in the form of a digital signal; the voice command carries beam information corresponding to the microphone array.
  • the beam information can be used to describe the time when each microphone receives the voice signal and the position of each microphone.
  • the digital signal processing unit 122 is used to determine the position range of the sound source corresponding to the voice signal based on the beam information, perform voice enhancement processing on the voice command based on the position range, and send the voice command after the voice enhancement process to the control unit 13 .
  • the number of analog-to-digital conversion units 121 can be equal to the number of microphones, that is, each analog-to-digital conversion unit 121 corresponds to a microphone, and each analog-to-digital conversion unit 121 is used to convert the voice signal from its corresponding microphone Voice commands converted to digital form.
  • the digital signal processing unit 122 can perform speech enhancement processing on the speech signal within the location range, and filter out the speech signal outside the location range, thereby reducing the The interference of environmental noise on voice signals improves the accuracy of voice recognition of terminal equipment and makes voice control more precise.
  • the terminal device 100 may further include a storage unit connected to the control unit 13, a power supply unit for supplying power to each unit, and the like.
  • the embodiment of the present application also provides a voice control system.
  • FIG. 3 is a schematic structural diagram of a voice control system provided by an embodiment of the present application.
  • the voice control system may include at least one controlled device and the terminal device 100 based on voice control in the embodiment corresponding to FIG. 1 or FIG. 2 .
  • the terminal device 100 is connected with at least one controlled device.
  • each functional unit in the embodiment can be integrated into one processing unit, or each unit can exist separately physically, or two or more units can be integrated into one unit, and the above-mentioned integrated units can be implemented in the form of hardware , can also be implemented in the form of software functional units.
  • the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Selective Calling Equipment (AREA)

Abstract

本申请适用于语音识别技术领域，提供了一种基于语音控制的终端设备及语音控制系统，其中，基于语音控制的终端设备包括：语音采集单元，用于采集语音信号；唤醒语识别单元，与所述语音采集单元连接，所述唤醒语识别单元用于对所述语音信号进行识别，并在识别出所述语音信号中包括预设的唤醒语时向控制单元发送中断信号；所述控制单元，与所述唤醒语识别单元连接，所述控制单元用于在接收到所述中断信号时开始监听来自所述唤醒语识别单元的语音指令，并在接收到所述语音指令时生成与所述语音指令对应的控制指令，从而不会占用控制单元较多的处理资源，提高了控制单元的资源利用率，且降低了控制单元的功耗。

Description

一种基于语音控制的终端设备及语音控制系统 技术领域
本申请属于语音识别技术领域，尤其涉及一种基于语音控制的终端设备及语音控制系统。
背景技术
随着语音识别技术的快速发展，基于语音识别技术的语音控制功能被广泛应用于各个领域中。例如，可以通过在终端设备(例如，机器人)的控制单元中内置语音识别算法来实现对终端设备的语音控制，进而实现对终端设备的智能化控制，提高终端设备的控制效率。
为了提高终端设备语音识别的准确率，现有的终端设备通常需要用户输入特定的唤醒语来唤醒其语音识别功能，在终端设备的语音识别功能被唤醒后终端设备才开始进行语音识别操作。然而，现有终端设备中的控制单元需要时刻监听用户是否输入唤醒语，这样会占用控制单元较多的处理资源，降低了控制单元的资源利用率，且会增加控制单元的功耗。
发明内容
有鉴于此，本申请实施例提供了一种基于语音控制的终端设备及语音控制系统，以解决现有终端设备中的控制单元需要时刻监听是否有唤醒语输入，占用控制单元较多处理资源，导致控制单元的资源利用率低，功耗高的技术问题。
第一方面，本申请实施例提供一种基于语音控制的终端设备，包括：
语音采集单元，用于采集语音信号；
唤醒语识别单元，与所述语音采集单元连接，所述唤醒语识别单元用于对所述语音信号进行识别，并在识别出所述语音信号中包括预设的唤醒语时向控制单元发送中断信号；
所述控制单元，与所述唤醒语识别单元连接，所述控制单元用于在接收到所述中断信号时开始监听来自所述唤醒语识别单元的语音指令，并在接收到所述语音指令时生成与所述语音指令对应的控制指令。
可选的，所述终端设备还包括连接在所述语音采集单元与所述唤醒语识别 单元之间的语音信号处理单元；所述语音信号处理单元用于对所述语音信号进行预处理，并向所述唤醒语识别单元发送预处理后的所述语音信号；所述预处理包括滤波处理和信号放大处理。
可选的，所述终端设备还包括与所述控制单元连接的通信单元；所述终端设备通过所述通信单元与至少一个受控设备连接；
所述控制单元用于在所述控制指令为针对所述受控设备的控制指令时，向所述通信单元发送所述控制指令；
所述通信单元用于接收来自所述控制单元的所述控制指令，并向所述受控设备发送所述控制指令。
可选的，所述终端设备还包括电机驱动单元、电机及运动组件；所述电机驱动单元与所述控制单元连接，所述电机与所述电机驱动单元和所述运动组件连接；
所述控制单元用于在所述控制指令为针对所述控制单元所在的终端设备的运动指令时，向所述电机驱动单元发送所述控制指令；
所述电机驱动单元用于基于所述控制指令驱动所述电机运转，以带动所述运动组件进行相应运动。
可选的，所述终端设备还包括与所述控制单元连接的音频输出单元；所述控制单元用于在接收到所述中断信号时生成携带有回复语的音频信号，并向所述音频输出单元发送所述音频信号；
所述音频输出单元用于接收所述音频信号，并播放所述回复语。
可选的，还包括与所述控制单元连接的状态指示单元；
所述状态指示单元用于通过指示灯指示所述控制单元所在的终端设备的状态。
可选的，所述语音采集单元为由多个麦克风组成的麦克风阵列。
可选的，所述多个麦克风线性排列，且相邻两个麦克风之间间隔预设距离。
可选的，所述唤醒语识别单元包括模数转换单元和数字信号处理单元；
所述模数转换单元用于将所述语音信号转换为数字信号形式的语音指令；所述语音指令中携带有与所述麦克风阵列对应的波束信息；所述波束信息用于描述各个所述麦克风接收到所述语音信号的时间以及各个所述麦克风的位置；
所述数字信号处理单元用于基于所述波束信息确定所述语音信号对应的声源所处的位置范围，并基于所述位置范围对所述语音指令进行语音增强处理， 并向所述控制单元发送语音增强处理后的所述语音指令。
第二方面，本申请实施例提供一种语音控制系统，包括至少一个受控设备以及如上述第一方面或第一方面的任一可选方式所述的基于语音控制的终端设备，所述终端设备与所述至少一个受控设备连接。
实施本申请实施例提供的基于语音控制的终端设备及语音控制系统具有以下有益效果：
本申请实施例提供的一种基于语音控制的终端设备，通过在语音采集单元与控制单元之间设置用于对语音信号进行识别的唤醒语识别单元，在唤醒语识别单元识别出语音信号中包括预设的唤醒语时，向控制单元发送一中断信号；控制单元在接收到该中断信号后才开始监听来自来自唤醒语识别单元的语音指令，即本申请中的唤醒语监听操作由唤醒语识别单元完成，控制单元在唤醒语识别单元监听到预设的唤醒语后才开启语音识别功能，从而不会占用控制单元较多的处理资源，提高了控制单元的资源利用率，且降低了控制单元的功耗。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种基于语音控制的终端设备的结构示意图；
图2为本申请另一实施例提供的一种基于语音控制的终端设备的结构示意图；
图3为本申请实施例提供的一种语音控制系统的结构示意图。
具体实施方式
需要说明的是，本申请实施例的实施方式部分使用的术语仅用于对本申请的具体实施例进行解释，而非旨在限定本申请。在本申请实施例的描述中，除非另有说明，“/”表示或的意思，例如，A/B可以表示A或B；本文中的“和/或”仅仅是一种描述关联物的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另 外，在本申请实施例的描述中，除非另有说明，“多个”是指两个或多于两个，“至少一个”、“一个或多个”是指一个、两个或两个以上。
以下，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”特征可以明示或者隐含地包括一个或者更多个该特征。
在本说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此，在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例，而是意味着“一个或多个但不是所有的实施例”，除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”，除非是以其他方式另外特别强调。
本申请实施例首先提供一种基于语音控制的终端设备。该终端设备可以是机器人或音响设备等。请参阅图1，为本申请实施例提供的一种基于语音控制的终端设备的结构示意图。如图1所示，该终端设备100可以包括语音采集单元11、唤醒语识别单元12及控制单元13。其中，唤醒语识别单元12与语音采集单元11和控制单元13连接。
本申请实施例中，语音采集单元11用于采集语音信号。
在具体应用中，语音采集单元11可以包括至少一个麦克风。语音采集单元11可以通过该至少一个麦克风来采集语音信号，并将采集到的语音信号发送给唤醒语识别单元12。其中，麦克风的数量和排列方式可以根据实际需求设置。
本申请实施例中，唤醒语识别单元12用于对语音信号进行识别，并在识别出语音信号中包括预设的唤醒语时向控制单元13发送中断信号。
在具体应用中，唤醒语识别单元12可以基于语音识别算法对来自语音采集单元11的语音信号进行识别，并判断语音信号中是否包括预设的唤醒语。
其中，预设的唤醒语用于唤醒终端设备100的语音控制功能。预设的唤醒语可以是一个字、一个词或一句话等，具体可以根据实际需求设置，此处不对其做特别限定。例如，预设的唤醒语可以是“小Q小Q”。
在本申请的一个实施例中，唤醒语识别单元12在判断出语音信号中包括预设的唤醒语时，可以向控制单元13发送中断信号。在本申请的另一个实施例中，唤醒语识别单元12在判断出语音信号中不包括预设的唤醒语时，可以不对该语 音信号进行响应，继续接收来自语音采集单元11的语音信号，直到识别出语音信号中包括预设的唤醒语时，向控制单元13发送中断信号。
在具体应用中，唤醒语识别单元12可以通过硬件中断的方式向控制单元13发送中断信号，也可以通过软件中断的方式向控制单元13发送中断信号。具体可以根据实际需求设置，此处不对其做特别限定。
唤醒语识别单元12向控制单元13发出中断信号后，若再次接收到来自语音采集单元11的语音信号，则可以将该语音信号转换为对应的语音指令，并将该语音指令发送给控制单元13。其中，语音信号为模拟信号，语音指令为语音信号对应的数字信号，唤醒语识别单元12可以对语音信号进行模数转换处理，进而得到语音信号对应的语音指令。
本申请实施例中，控制单元13用于在接收到中断信号时开始监听来自唤醒语识别单元12的语音指令，并在接收到语音指令时生成与该语音指令对应的控制指令。
在一种可能的实现方式中，控制指令可以包括针对终端设备自身的控制指令，例如，运动指令。运动指令中可以包括终端设备的运动参数，例如，终端设备的运动路线、运动速度和/或旋转角速度等。该实现方式中，终端设备100可以通过执行该控制指令来实现对自身的控制。
在另一种可能的实现方式中，控制指令可以包括针对与终端设备连接的其他设备的控制指令。该实现方式中，控制单元13可以将控制指令发送给其他设备，以实现对其他设备的控制。
在具体应用中，控制单元13可以包括微处理单元(micro controller unit，MCU)、单片机或先进的精简指令微处理器(Advanced RISC Machines，ARM)等，具体可以根据实际需求设置，此处不对其做特别限定。
以上可以看出，本实施例提供的基于语音控制的终端设备，通过在语音采集单元与控制单元之间设置用于对语音信号进行识别的唤醒语识别单元，在唤醒语识别单元识别出语音信号中包括预设的唤醒语时，向控制单元发送一中断信号；控制单元在接收到该中断信号后才开始监听来自来自唤醒语识别单元的语音指令，即本申请中的唤醒语监听操作由唤醒语识别单元完成，控制单元在唤醒语识别单元监听到预设的唤醒语后才开启语音识别功能，从而不会占用控制单元较多的处理资源，提高了控制单元的资源利用率，且降低了控制单元的功耗。
请参阅图2，为本申请另一实施例提供的一种基于语音控制的终端设备的结构示意图。如图2所示，本实施例相对于图1对应的实施例的区别在于，本实施例中的语音采集单元11可以为由多个麦克风(麦克风1～麦克风n)组成的麦克风阵列。示例性的，该多个麦克风可以呈线性排布，且每相邻两个麦克风之间间隔一定距离。当然，该多个麦克风还可以呈其他排列方式。
可以理解的是，不同麦克风在排列位置上的差异会导致同一声源发出的语音信号到达不同麦克风的时间不同。因此，利用语音信号达到各个麦克风的时间信息以及各个麦克风的位置信息可以计算出声源所处的位置范围。
本实施例中，麦克风在向唤醒语识别单元12传输语音信号的同时，还传输其采集到该语音信号的时间。唤醒语识别单元12可以根据各个麦克风采集到语音信号的时间以及各个麦克风的位置信息计算出声源所处的位置范围，进而对该位置范围内的语音信号进行语音增强处理，对该位置范围外的语音信号进行滤除。其中，各个麦克风的位置信息可以存储在唤醒语识别单元12中。
本实施例采用麦克风阵列来采集语音信号，利用麦克风阵列的强指向性对声源进行定位，并对声源所处的位置范围内的的语音信号进行增强，对声源所处的位置范围外的信号进行滤除，从而可以降低环境噪音对语音信号的干扰，提高了终端设备语音识别的准确率，使得语音控制更为精准。
在本申请的又一个实施例中，基于语音控制的终端设备100还包括连接在语音采集单元11与唤醒语识别单元12之间的语音信号处理单元14。
其中，语音信号处理单元14用于对语音信号进行预处理，并向唤醒语识别单元12发送预处理后的语音信号。
在具体应用中，预处理可以包括滤波处理和信号放大处理。基于此，语音信号处理单元14可以包括滤波电路141和信号放大电路142。
其中，滤波电路141可以是硬件滤波电路(例如，可以是由电阻和电容等元器件组成的滤波电路)，也可以是成品滤波器，此处不对其做特别限定。
信号放大电路142可以是硬件信号放大电路。实例中的，信号放大电路142可以包括低噪声放大器。
本实施例通过在语音采集单元与唤醒语识别单元之间设置语音信号处理单元，可以滤除语音信号中的杂音(例如环境噪音)并对语音信号进行信号放大，从而可以提高唤醒语识别单元和控制单元的语音识别准确率。
在本申请的又一个实施例中，基于语音控制的终端设备100还包括与控制 单元13连接的通信单元15。终端设备可以通过通信单元15与至少一个受控设备连接。在具体应用中，受控设备可以是智能家居设备，包括但不限于：智能灯、空调、冰箱、洗衣机、晾衣架、窗帘、电视及视频监控器等。受控设备的数目可以根据实际需求设置，此处不对其做特别限定。
在一种可能的实现方式中，通信单元15可以是无线通信单元，例如，可以是基于无线保真(wireless fidelity，WIFI)协议的通信单元、基于紫蜂(ZigBee)协议或基于蓝牙协议的通信单元。
在另一种可能的实现方式种，通信单元15可以是有线通信单元，例如，可以是通用串行总线(Universal Serial Bus，USB)接口单元。
本实施例中，控制单元13用于在控制指令为针对受控设备的控制指令时，向通信单元15发送控制指令。通信单元15用于接收来自控制单元13的控制指令，并向受控设备发送控制指令。
本实施例中，由于控制单元13需要将控制指令发送给与终端设备连接的受控设备，因此控制单元13在生成控制指令时需要终端设备与受控设备之间的通信协议，即控制单元13生成的控制指令的数据结构要符合该通信协议的要求。
在一种可能的方式中，控制指令的数据结构可以如下表1所示。
表1
数据头 数据长度 功能码 数据位 校验位
Byte0，Byte1 Byte2 Byte3 Byte4-Byte n Byte n+1
其中，数据头为控制指令的起始字节，用于表示控制指令的开始。示例性的，数据头可以通过两个字节(即Byte0和Byte1)来表示。作为示例而非限定，Byte0和Byte1均可以为十六进制数0xF8(即二进制数11111000)。
数据长度用于表示控制指令的有效数据长度，即表1中包括数据头在内的所有字节的长度。
功能码用于表示控制指令所实现的功能类别。不同类别的功能通过该功能码进行唯一标识。示例性的，功能码的定义可以如下：
当功能码为十六进制数0x00，表示用于实现对终端设备的运动控制功能。
当功能码为十六进制数0x01，表示用于实现对智能灯的控制功能。
当功能码为十六进制数0x02，表示用于实现对空调的控制功能。
当功能码为十六进制数0x03，表示用于实现对冰箱的控制功能。
当功能码为十六进制数0x04，表示用于实现对洗衣机的控制功能。
当功能码为十六进制数0x05，表示用于实现对晾衣架的控制功能。
当功能码为十六进制数0x06，表示用于实现对窗帘的控制功能。
当功能码为十六进制数0x07，表示用于实现对电视的控制功能。
当功能码为十六进制数0x08，表示用于实现对视频监控器的控制功能。
数据位用于记载有效控制内容。有效控制内容用于描述对目标设备的控制方式，即对目标设备进行怎样的控制。数据位的长度根据控制内容的不同而不同，具体可以根据实际需求确定，此处不对数据位的长度做特别限定。其中，目标设备可以是终端设备100本身，也可以是与终端设备100连接的受控设备。
校验码用于验证控制指令的有效性。校验码可以是基于预设的校验码生成策略生成的。示例性的，校验码生成策略可以为：从控制指令的第一个字节开始，将控制指令中的第一个字节与第二字节进行异或运算，得到第一个异或值；将第一个异或值与第三字节进行异或运算，得到第二个异或值；以此类推，直至求得第n-1个异或值为止，将第n-1个异或值作为校验码。
受控设备接收到数据后，可以先通过数据头来识别控制指令，再基于控制指令中的功能码来识别该控制指令是否是针对当前受控设备自身的。如果控制指令是针对当前受控设备自身的，则基于控制指令中的校验码对控制指令的有效性进行验证，在确定控制数据有效后基于控制指令中的数据位实现相应控制。
本实施例通过在终端设备中增加通信单元，可以使终端设备通过通信单元与受控设备进行连接，进而实现对受控设备的语音控制。
在本申请的又一个实施例中，基于语音控制的终端设备100还包括电机驱动单元16、电机17及运动组件18。其中，电机驱动单元16与控制单元13连接，电机17与电机驱动单元16和运动组件18连接。
本实施例中，控制单元13用于在控制指令为针对终端设备自身的运动指令时，向电机驱动单元16发送该控制指令。该控制指令中可以携带有终端设备的运动参数，例如，终端设备的运动路线、运动速度和/或旋转角速度等。
电机驱动单元16用于基于该控制指令驱动电机17运转，以带动运动组件18进行相应运动。
本实施例通过在终端设备中设置电机驱动单元、电机及运动组件，可以实现语音控制终端设备运动，从而提高了对终端设备控制的便捷性。
在本申请的又一个实施例中，基于语音控制的终端设备100还包括与控制 单元13连接的音频输出单元19。本实施例中，控制单元13用于在接收到中断信号时生成携带有回复语的音频信号，并向音频输出单元19发送该音频信号。其中，音频输出单元19用于接收音频信号，并播放音频信号中的回复语。
本实施例中，音频输出单元19播放回复语的目的是为了告知用户终端设备的语音监听功能已开启，用户可以开始对终端设备进行语音控制。
其中，回复语可以根据实际需求设置，此处不对其做特别限定。例如，回复语可以为“灵犀灵犀”。
在具体应用中，音频输出单元19可以包括信号放大电路和扬声器(未图示)。其中，信号放大电路与控制单元13和扬声器连接。信号放大电路用于对携带有回复语的音频信号进行信号放大处理，并将信号放大处理后的音频信号发送给扬声器。扬声器用于对音频信号中的回复语进行播放。
本实施例通过在终端设备中设置音频输出单元，通过音频输出单元输出与用户发出的语音信号对应的回复语，使用户可以及时获知终端设备的状态。
在本申请的又一个实施例中，基于语音控制的终端设备100还包括与控制单元13连接的状态指示单元20。其中，状态指示单元20用于通过指示灯指示终端设备100的状态。示例性的，终端设备100的状态包括但不限于终端设备100中的控制单元13的语音监听状态。
在具体应用中，状态指示单元20可以包括发光二极管(light-emitting diode，LED)，通过控制LED发出不同颜色的光来对终端设备的不同状态进行指示。
在本申请的又一个实施例中，唤醒语识别单元12可以包括模数转换单元121和数字信号处理单元122。
其中，模数转换单元121用于将语音信号转换为数字信号形式的语音指令；语音指令中携带有与麦克风阵列对应的波束信息。波束信息可以用于描述各个麦克风接收到语音信号的时间以及各个麦克风的位置。
数字信号处理单元122用于基于波束信息确定语音信号对应的声源所处的位置范围，并基于该位置范围对语音指令进行语音增强处理，并向控制单元13发送语音增强处理后的语音指令。
在具体应用中，模数转换单元121的数目可以与麦克风的数目相等，即，每个模数转换单元121对应一个麦克风，每个模数转换单元121用于将来自其对应的麦克风的语音信号转换为数字形式的语音指令。
本实施例中，数字信号处理单元122确定出声源所处的位置范围后，可以 对该位置范围内的语音信号进行语音增强处理，对该位置范围外的语音信号进行滤除，从而可以降低环境噪音对语音信号的干扰，提高了终端设备语音识别的准确率，使得语音控制更为精准。
在本申请的又一个实施例中，终端设备100还可以包括与控制单元13连接的存储单元以及为各个单元进行供电的供电单元等。
本申请实施例还提供一种语音控制系统。请参阅图3，为本申请实施例提供的一种语音控制系统的结构示意图。如图3所示，该语音控制系统可以包括至少一个受控设备以及图1或图2对应的实施例中的基于语音控制的终端设备100。该终端设备100与至少一个受控设备连接。
需要说明的是，关于终端设备100的说明具体可以参考图1和图2以及图1和图2对应的实施例中的相关描述，此处不再对其进行赘述。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元完成，即将语音播报装置的内部结构划分成不同的功能单元，以完成以上描述的全部或者部分功能。实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参照其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申 请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种基于语音控制的终端设备，其特征在于，包括：
    语音采集单元，用于采集语音信号；
    唤醒语识别单元，与所述语音采集单元连接，所述唤醒语识别单元用于对所述语音信号进行识别，并在识别出所述语音信号中包括预设的唤醒语时向控制单元发送中断信号；
    所述控制单元，与所述唤醒语识别单元连接，所述控制单元用于在接收到所述中断信号时开始监听来自所述唤醒语识别单元的语音指令，并在接收到所述语音指令时生成与所述语音指令对应的控制指令。
  2. 根据权利要求1所述的终端设备，其特征在于，还包括连接在所述语音采集单元与所述唤醒语识别单元之间的语音信号处理单元；所述语音信号处理单元用于对所述语音信号进行预处理，并向所述唤醒语识别单元发送预处理后的所述语音信号；所述预处理包括滤波处理和信号放大处理。
  3. 根据权利要求1所述的终端设备，其特征在于，还包括与所述控制单元连接的通信单元；所述终端设备通过所述通信单元与至少一个受控设备连接；
    所述控制单元用于在所述控制指令为针对所述受控设备的控制指令时，向所述通信单元发送所述控制指令；
    所述通信单元用于接收来自所述控制单元的所述控制指令，并向所述受控设备发送所述控制指令。
  4. 根据权利要求1所述的终端设备，其特征在于，还包括电机驱动单元、电机及运动组件；所述电机驱动单元与所述控制单元连接，所述电机与所述电机驱动单元和所述运动组件连接；
    所述控制单元用于在所述控制指令为针对所述控制单元所在的终端设备的运动指令时，向所述电机驱动单元发送所述控制指令；
    所述电机驱动单元用于基于所述控制指令驱动所述电机运转，以带动所述运动组件进行相应运动。
  5. 根据权利要求1所述的终端设备，其特征在于，还包括与所述控制单元连接的音频输出单元；所述控制单元用于在接收到所述中断信号时生成携带有回复语的音频信号，并向所述音频输出单元发送所述音频信号；
    所述音频输出单元用于接收所述音频信号，并播放所述回复语。
  6. 根据权利要求1所述的终端设备，其特征在于，还包括与所述控制单元 连接的状态指示单元；
    所述状态指示单元用于通过指示灯指示所述控制单元所在的终端设备的状态。
  7. 根据权利要求1至6任一项所述的终端设备，其特征在于，所述语音采集单元为由多个麦克风组成的麦克风阵列。
  8. 根据权利要求7所述的终端设备，其特征在于，所述多个麦克风线性排列，且相邻两个麦克风之间间隔预设距离。
  9. 根据权利要求7所述的终端设备，其特征在于，所述唤醒语识别单元包括模数转换单元和数字信号处理单元；
    所述模数转换单元用于将所述语音信号转换为数字信号形式的语音指令；所述语音指令中携带有与所述麦克风阵列对应的波束信息；所述波束信息用于描述各个所述麦克风接收到所述语音信号的时间以及各个所述麦克风的位置；
    所述数字信号处理单元用于基于所述波束信息确定所述语音信号对应的声源所处的位置范围，并基于所述位置范围对所述语音指令进行语音增强处理，并向所述控制单元发送语音增强处理后的所述语音指令。
  10. 一种语音控制系统，其特征在于，包括至少一个受控设备以及如权利要求1至9任一项所述的基于语音控制的终端设备，所述终端设备与所述至少一个受控设备连接。
PCT/CN2021/137611 2021-11-30 2021-12-13 一种基于语音控制的终端设备及语音控制系统 WO2023097761A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111446783.2 2021-11-30
CN202111446783.2A CN114155851A (zh) 2021-11-30 2021-11-30 一种基于语音控制的终端设备及语音控制系统

Publications (1)

Publication Number Publication Date
WO2023097761A1 true WO2023097761A1 (zh) 2023-06-08

Family

ID=80455504

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137611 WO2023097761A1 (zh) 2021-11-30 2021-12-13 一种基于语音控制的终端设备及语音控制系统

Country Status (2)

Country Link
CN (1) CN114155851A (zh)
WO (1) WO2023097761A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108597507A (zh) * 2018-03-14 2018-09-28 百度在线网络技术（北京）有限公司 远场语音功能实现方法、设备、系统及存储介质
CN108877805A (zh) * 2018-06-29 2018-11-23 上海与德通讯技术有限公司 语音处理模组和具有语音功能的终端
EP3413304A2 (en) * 2017-05-19 2018-12-12 LG Electronics Inc. Method for operating home appliance and voice recognition server system
CN110223687A (zh) * 2019-06-03 2019-09-10 Oppo广东移动通信有限公司 指令执行方法、装置、存储介质及电子设备
CN110858483A (zh) * 2018-08-23 2020-03-03 深圳市冠旭电子股份有限公司 智能设备、语音唤醒方法、语音唤醒装置及存储介质
CN113259793A (zh) * 2020-02-07 2021-08-13 杭州智芯科微电子科技有限公司 智能麦克风及其信号处理方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3413304A2 (en) * 2017-05-19 2018-12-12 LG Electronics Inc. Method for operating home appliance and voice recognition server system
CN108597507A (zh) * 2018-03-14 2018-09-28 百度在线网络技术（北京）有限公司 远场语音功能实现方法、设备、系统及存储介质
CN108877805A (zh) * 2018-06-29 2018-11-23 上海与德通讯技术有限公司 语音处理模组和具有语音功能的终端
CN110858483A (zh) * 2018-08-23 2020-03-03 深圳市冠旭电子股份有限公司 智能设备、语音唤醒方法、语音唤醒装置及存储介质
CN110223687A (zh) * 2019-06-03 2019-09-10 Oppo广东移动通信有限公司 指令执行方法、装置、存储介质及电子设备
CN113259793A (zh) * 2020-02-07 2021-08-13 杭州智芯科微电子科技有限公司 智能麦克风及其信号处理方法

Also Published As

Publication number Publication date
CN114155851A (zh) 2022-03-08

Similar Documents

Publication Publication Date Title
CN106847298B (zh) 一种基于弥漫式语音交互的拾音方法和装置
CN104808496B (zh) 一种智能家居控制系统及访问方法
CN106507244A (zh) 一种中控系统
CN104538030A (zh) 一种可以通过语音控制家电的控制系统与方法
CN104866067A (zh) 一种低功耗控制方法及电子设备
WO2020186756A1 (zh) 空气调节设备的控制方法、装置、空气调节设备和服务器
CN106782519A (zh) 一种机器人
CN104235996A (zh) 空调器音频控制方法及装置和空调器
CN207742924U (zh) 基于智能语音控制的遥控器
CN108592349A (zh) 一种空调控制系统
TW201908920A (zh) 數位語音助理之操作系統
WO2023097761A1 (zh) 一种基于语音控制的终端设备及语音控制系统
CN206134251U (zh) 电动晾衣机的控制系统及电动晾衣机
CN113674738A (zh) 一种全屋分布式语音的系统和方法
CN204480661U (zh) 语音控制装置
CN213392751U (zh) 基于神经网络芯片的语音交互智能电风扇及电风扇系统
CN208538475U (zh) 一种智能机器人
CN107635178A (zh) 一种具有识别语音功能的拉杆音箱
CN111415657A (zh) 一种去中心化设备、多设备系统及其语音控制方法
CN110568832A (zh) 远程控制器、协调器、智能家居设备及远程控制系统
CN102281664B (zh) 利用交互式灯光控制总线实现的灯具控制方法
CN109458720A (zh) 一种中央空调系统
CN108093348A (zh) 一种智能音箱的扩展器及智能音箱及智能音箱的多点交互方法
CN211828111U (zh) 语音交互系统
CN104078042A (zh) 一种电子设备及一种信息处理的方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21966186

Country of ref document: EP

Kind code of ref document: A1